PLATON: A force-directed placement algorithm for 3D Optical Networks-on-Chip

Anja Von Beuningen, Ulf Schlichtmann

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

18 Scopus citations

Abstract

Optical Networks-on-Chip (ONoCs) are a promising technology to further increase the bandwidth and decrease the power consumption of today's multicore systems. To determine the laser power consumption of an ONoC, the physical design of the system is indispensible. The only place and route tool for 3D ONoCs already proposed in the literature badly scales with the increasing number of optical devices. Thus, within this contribution we present the first force-directed placement algorithm for 3D optical NoCs. Our algorithm decreases the runtime up to 99.7% compared to the state-of-the-art placer. Using our algorithm large topologies can be placed within a short runtime.

Original languageEnglish
Title of host publicationISPD 2016 - Proceedings of the 2016 International Symposium on Physical Design
PublisherAssociation for Computing Machinery
Pages27-34
Number of pages8
ISBN (Electronic)9781450340397
DOIs
StatePublished - 3 Apr 2016
Event2016 International Symposium on Physical Design, ISPD 2016 - Santa Rosa, United States
Duration: 3 Apr 20166 Apr 2016

Publication series

NameProceedings of the International Symposium on Physical Design
Volume03-06-April-2016

Conference

Conference2016 International Symposium on Physical Design, ISPD 2016
Country/TerritoryUnited States
CitySanta Rosa
Period3/04/166/04/16

Keywords

  • Optical Networks-on-Chip
  • Placement
  • Silicon photonics

Fingerprint

Dive into the research topics of 'PLATON: A force-directed placement algorithm for 3D Optical Networks-on-Chip'. Together they form a unique fingerprint.

Cite this